© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 7165
    Prev
    Next
    INDEX
    Explanations

    adjectives used to describe materials or fabrics

    oai_token-act-pair · gpt-3.5-turbo

    the word "th" in various contexts or forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    staking
    -0.82
    ITED
    -0.81
    GMT
    -0.77
     Canaver
    -0.66
    915
    -0.65
    assetsadobe
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.62
    fman
    -0.61
     sterling
    -0.60
    enhagen
    -0.59
    POSITIVE LOGITS
    ulhu
    1.20
    ttp
    1.11
    umbnail
    1.08
    orne
    1.06
    ousands
    1.02
    ieving
    0.99
    ousand
    0.96
    irteen
    0.94
    ieves
    0.94
    irty
    0.94
    Activations Density 0.042%

    No Known Activations